Tag
This paper presents a training-free LLM-based candidate generation pipeline for vacation rental marketplaces, using an off-the-shelf LLM to synthesize semantic queries and dense retrieval to complement collaborative filtering, significantly improving coverage for long-tail properties while maintaining performance on well-served ones.
F-GRPO proposes a factorized group-relative policy optimization framework that unifies candidate generation and ranking in a single autoregressive LLM, addressing credit assignment issues and improving top-ranked performance across sequential recommendation and multi-hop QA benchmarks.